Scopus Indexed. Syam Babu Vadlamudi Department of Electronics & Communication, MLR Institute of Technology. Koppula Srinivas Rao

Transcription

1 International Journal of Mechanical Engineering and Technology (IJMET) Volume 8, Issue 7, July 2017, pp , Article ID: IJMET_08_07_016 Available online at aeme.com/ijm MET/issues.as asp?jtype=ijm MET&VType=8&IType= =7 ISSN Print: and ISSN Online: IAEME Publication Scopus Indexed REGION OF INTEREST (ROI)-BASED IMAGE COMPRESSION FOR TELEMEDICINE APPLICATIONS Syam Babu Vadlamudi Department of Electronics & Communication, MLR Institute of Technology y, Hyderabad, India Koppula Srinivas Rao Department of Information Technology, MLR Institute of Technology, Hyderabad, India A L Siridhara Department of Electronics & Communication, MLR Institute of Technology y, Hyderabad, India R Karthik Department of Electronics & Communication, MLR Institute of Technology y, Hyderabad, India ABSTRACT This as the medical imaging and telemedicine has been developing on large scale but with the ncreasing demand of storing and sending the medical image results in lack of sufficient memory spaces and transmission bandwidth. To fix these issues compression was introduced. In medical imaging losslesss compression schemess are under intensivee interest because theree is no loss of information. The only small part is more useful out of the whole image. Region of Interest Based Coding techniques are more considerable in medical field (for DICOM Images) for the sake of efficient compression and transmission. The current work begins with separation of the image. Finally compression is performed to reduce the storage and network bandwidth. Lossy compression for Non ROI image is applied by using spiht algorithm and lossless compression for ROI part of an image by transforming the image to discrete wavelet transform using huffman coding. Key words: DICOM image; integer wavelet transform; lossless compression; medical image compression; region-based coding; telemedicine. Cite this Article: Syam Babu Vadlamudi, Koppula Srinivas Rao, A L Siridhara and R Karthik. Region of Interest (ROI)-based Image Compression for Telemedicine Applications. International Journal of Mechanical Engineering and Technology, 8(7), 2017, pp http: :// me.com/ijm MET/issues.a asp?jtype=i IJMET&VType=8&ITy ype=7 133 editor@iaeme..com

2 Region of Interest (ROI)-based Image Compression for Telemedicine Applications 1. INTRODUCTION Usually a huge amount of data is produced CT scanned (Computed Tomography) images and MRI scanned (Magnetic Resonance Imaging) images which is difficult for transmission through network. Multispecialty hospitals can store this data but it is difficult for medium scale hospitals to store this data this complexity can be reduced by using compression techniques. There is also transfer or exchange of medical image data such as X-ray, ultrasound images for the diagnostic purpose. The main goal of telemedicine to use the advance technology to improve the health of the patients in those areas where geographical distance becomes the barrier. Telemedicine for the most part has two essential capacities. First is the Transfer of Patient's therapeutic information as an option of patient moving starting with one spot then onto the next.video Conferencing between patient end and master specialists for discussion, treatment and follow up. After direct communication, at the multispecialty hospital senior doctor checks the information and sends the report back to the nearby, who gives treatment to the patient. In this information and communication technologies are used.it reduces the stress level in patients due to the travel time and it s expensive. It is more economical as it decreased go time. DICOM is the most comprehensive and accepted version of an imaging communications standard. DICOM format has a header which contains information about the image, imaging modality and information about the patient. The header also contains the information about the type of media (CT, MRI, audio recording, etc.) and the image dimensions. Body of DICOM standard contains information objects such as medical reports, audio recordings and images. The coding decoding algorithm must take care of other information in the DICOM file. Also, the algorithms should accept the input image in DICOM format at encoder end and produce DICOM file at decoder end [1]. Basic concept of Region of Interest (ROI) is introduced due to limitations of lossy and lossless compression techniques. For well-known lossless compression technique the compression ratio is approximately 25% of original size, whereas for lossy encoders the compression ratio is much higher (up to 1% also), but there is loss in the data. Now this loss may hamper some diagnostically important part of the image. Hence, there is a need of some hybrid technique which will take care of diagnostically important part (ROI) as well as will provide high compression ratio.the functionality of ROI is important in medical applications where certain parts of the image are of higher diagnostic importance than others. 2. NEED FOR COMPRESSION In telemedicine, patient s medical information is being transferred from one multispecialty hospital to the local hospitals. Hospital stores this information for the future use. But the size of medical image is large. Multispecialty hospital produces large number of images per patient. The amount of images produces by the hospital takes the storage of 5 to 15 GB per day. So it is too difficult to manage the storage system in the hospitals because it is mandatory for hospital to store the medical record of each patient and moreover to send these images over the network needs high bandwidth this increases the transmission cost and complexity. In rural area, there are many network issues which may cause the problem in transmission of data. To deal with these problems compression techniques was introduced. Compression decreases the size of images. Compression of image is of two types lossy compression and lossless compression. Lossy compression techniques are used where loss can be accepted i.e. Non region of interest. Lossless compression techniques are used where loss cannot be accepted i.e. Region of interest [2]. 134 editor@iaeme.com

3 Syam Babu Vadlamudi, Koppula Srinivas Rao, A L Siridhara and R Karthik 3. REGION OF INTEREST The medical image includes three parts in image they are ROI (region of interest), non ROI and background. These part have their own advantages. ROI is the most critical part of the image that located over very small regions of the image. Non ROI is also included so that user can easily identify the most critical part from the whole image [3-4].. Part other than image contents tents is known as background and this is the most ignored part of the image. In medical field, the ROI which is critical part need to be compressed with high quality compression without any loss than other parts of image i.e. NON NON-ROI ROI and background. The cr critical itical parts from the image obliged to be transmitted first or at higher need amid the transmission for telemedi telemedicine cine purposes. Figure 1 shows the three different parts of the medical image. Figure 1 Lung Image The background is made zero using: img img[i, j] x_th,, then img img[i, j] = 0. (1) Here, X_th is the threshold value of background of the image (img). As the background is not required reducing the background contents to zero also accounts for complete lossless compression, producing a ready to process image. Morphological operations are effectively used, which contain a value of 1 in the foreground and a value of 0 in the background. Then the mask is logically AND AND-ed ed with the image to separate-out out ROI part (IMG_ROI) and Non-ROI Non ROI image part as shown in equation 22. ROI _mask&& &&img = I MG_ROI. MG. (2) The two separated parts can be processed separately as per the requirement, i.e., ROI part will be processed by lossless technique, while Non-ROI Non ROI will be compressed wit withh accepted lossy compression methods; 3.1. ROI and non-roi non ROI processing Lossless compression, Progressive transmission and RBC are important functionalities for a compression scheme helpful helpful in telemedicine application application.. User can select ROI of any arbitrary shape. ROI is compressed with lossless version of compression technique such as Huffman, Arithmetic, RLE, LZW, ZIP, etc., while Non Non-ROI ROI is compressed by SPIHT asp 135 editor@iaeme.com

4 Region of Interest (ROI)-based Image Compression for Telemedicine e Applications Figure 2 Cross sectional view of medical image (statistical representation) 4. DISCRET WAVELET TRANSFORM Most of the image compression techniques use DWT (Discrete wavelett Transform) based transformation for compression. DWT is used for image decomposition and an N X N image is decomposed using DWT into hierarchical blocks the decomposition is carried out until the sub block is of size 8 x 8. The Discrete Wavelet Transform (DWT) is an efficient and useful tool for signal and image processing applications and will be adopted in many emerging standards, starting with the new compression standard JPEG2000. This growing success is due to the achievements reached in the field of mathematics, to its multiresolution processing capabilities, and also to the wide range of filters that can be provided. These features allow the DWT to be tailored to suit a wide range of applications. The advantages of DWT are: Figure 3 Block Diagram It is faster than other traditional WT. There is no need of temporary memory. It generates integer coefficients. So it has low computational complexity as compared with other WT. It is completely reversible Algorithm A new algorithm for implementation is presented as, Read the image from and get dimensions for given input image. Apply segmentation algorithm and separate background from image. o Detect ROI part of the image. o Separate ROI and Non-ROI of the image. o Apply compression algorithm. 136 editor@iaeme..com

5 Syam Babu Vadlamudi, Koppula Srinivas Rao, A L Siridhara and R Karthik 5. EXPERIMENTAL RESULTS Original image formatted in DICOM format of size 256 X 256 with 8 bit resolution is input to software. The compressed image is the image which is generated at the decoder side after reconstruction process. The output of encoder is a bit stream of numbers arranged in a manner so as to support the progressive transmission, with initial part as a ROI compressed with run length encoding. This bit stream is transmitted over the telemedicine medicine network using GSM mobile device (a) (b) (c) (d) Figure 4 (a) Original Image (b) Region of Interest (c) Non region of interest (d) Compression of ROI (a) (b) (c) Figure 5 (a) Compression of Non ROI (b) Decompression of ROI (c) Decompression of Non ROI asp 137 editor@iaeme.com

6 Region of Interest (ROI)-based Image Compression for Telemedicine e Applications Here the roi image is compressed with lossless compression so that there is no losss of data. Here we used descrete wavelet transform to convert the image from time domain to frequency domain because long distance communication is only possible in frequency domain. after conversion by using huffman coding compression is done. Here the non-roi image is compressed with lossy compression becausee non roi is not that important as roi. Even in non roi compression we use discretee wavelet transform to convert the image from time domain to frequency domain. Here we use spiht algorithm for lossy compression. The compression of ROI is done by using huffman encoding technique and by applying discrete wavelet transform Here the image roi is decompressed. There is no losss of data after decompression. Decompression is only done after the image is transmitted through a communication channel. Here after non-roi is decompression of image there is loss of data. Our main aim is to send the image through communication channel so after the decompression of nonn roi image some data gets reducedd so that it can be transmitted throughh communication channel. 6. MEASUREMENTS FOR LOSSY COMPRESSION METHOD In lossy compression technique the decompressed image is not identical to the original image, but reasonably close to it and is used in many applications. In lossy methods, a little information is lost as the high compression ratio is the main objective. It is a trade-off between image distortion and the compression ratio. Some distortion measurements are often used to quantify the quality of the reconstructed image as welll as the compression ratio (the ratio of the size of the original image to the size of the compressed image). The commonly used objective distortion measurements, which are derived from statistical terms, are the RMSE (root mean square error), the NMSE (normalized mean square error) and the PSNR (peak signal-to-noise ratio). These measurements are defined as follows. 7. CONCLUSIONS This paper discusses ROI-based medical image compression n. DWT is recommended for medical image applications because of the perfect reconstruction with low computation complexity. Different techniques can be used for non-roi compression of medical images. Non-ROI part must be encoded, because it gives the accurate position of ROI. ROI based coding is used along with compression for non- ROI reflects an accurate measure of performance. ROI based compression provides better performance compared with other methods. The proposed technique is lesss complexity and allows progressive transmission in telemedicine applications. ACKNOWLEDGMENT The authors would like to thank the MLR Institute of Technology, Hyderabad, India for financially supporting this work under research grant and also thank General Hospital, Hyderabad for valuable help and support. 138 editor@iaeme..com

7 REFERENCES Syam Babu Vadlamudi, Koppula Srinivas Rao, A L Siridhara and R Karthik [1] Xiaodi Hou and Liqing Zhang, Saliency Detection: A Spectral Residual Approach, IEEE Conference on Computer Vision and Pattern Recognition, 2007, pp.1-8. [2] Onsy Abdel Alim1, Nadder Hamdy and Wesam Gamal El-Din, Determination of the Region of Interest in the Compression of Biomedical Images, 24th National Radio Science Conference, 2007,pp.1 6. [3] Miaou S G, Ke F S and Chen S C, A lossless compression method for medical image sequences using JPEG-LS and interframe coding. IEEE Trans. Inform. Technol. Biomed., 2009, 13(5): [4] Maglogiannis I and Kormentzas G, Wavelet-based compression with ROI coding support for mobile access to DICOM images over heterogeneous radio networks. Trans. Inform. Technol. Biomed, 2009, 13(4): [5] T.M. Amarunnishad, Meekha Merina George, Colour Image Compression Using Block Truncation Coding and Genetic Algorithm. International Journal of Advanced Research in Engineering and Technology (IJARET), 5(4), 2014, pp [6] A.H.M. Jaffar Iqbal Barbhuiya, Tahera Akhtar Laskar, K. Hemachandran. An Approach for Color Image Compression of BMP and TIFF Images Using DCT and DWT. International Journal of Computer Engineering and Technology (IJCET), 6(1), 2015, pp [7] JNVR Swarup Kumar and R Deepika. An Optimized Block Estimation Based Image Compression and Decompression Algorithm. International Journal of Computer Engineering and Technology, 7 (1), 2016, pp editor@iaeme.com